© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9572
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper names and surnames, particularly those with non-standard or non-English characters.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */),
    -0.53
    EDEFAULT
    -0.50
     <<<<<<<<<<<<<<
    -0.43
    səhifə
    -0.41
    MethodType
    -0.40
    cotch
    -0.38
     Dami
    -0.37
     ſtand
    -0.37
    instancetype
    -0.36
    ajs
    -0.36
    POSITIVE LOGITS
     Z
    0.55
    ValueStyle
    0.49
     Zin
    0.47
    Билгалдахарш
    0.44
     ZO
    0.43
     Zuh
    0.41
     Zol
    0.41
     Zoological
    0.40
     Zou
    0.40
     zom
    0.40
    Activations Density 0.204%

    No Known Activations